[PATCH net-next v2 4/4] net: mvneta: Spread out the TX queues management on all CPUs

[Gregory CLEMENT]

With this patch each CPU is associated with its own set of TX queues. In
the same time the SKB received in mvneta_tx is bound to the queue
associated to the CPU sending the data. Thanks to this the next IRQ will
be received on the same CPU allowing sending more data.

It will also allow to have a more predictable behavior regarding
throughput and latency when having multiple threads sending out data on
different CPUs.

As an example on Armada XP GP, with an iperf bound to a CPU and a ping
bound to another CPU, without this patch the ping round trip was about
2.5ms (and could reach 3s!), whereas with this patch it was around
0.7ms (and sometime it went to 1.2ms).

Suggested-by: Arnd Bergmann <arnd at arndb.de>
Signed-off-by: Gregory CLEMENT <gregory.clement at free-electrons.com>
---
 drivers/net/ethernet/marvell/mvneta.c | 48 ++++++++++++++++++++++++++---------
 1 file changed, 36 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index e0dba6869605..bb5e29daac0b 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -110,6 +110,7 @@
 #define      MVNETA_CPU_RXQ_ACCESS_ALL_MASK      0x000000ff
 #define      MVNETA_CPU_TXQ_ACCESS_ALL_MASK      0x0000ff00
 #define      MVNETA_CPU_RXQ_ACCESS(rxq)		 BIT(rxq)
+#define      MVNETA_CPU_TXQ_ACCESS(txq)		 BIT(txq + 8)
 #define MVNETA_RXQ_TIME_COAL_REG(q)              (0x2580 + ((q) << 2))
 
 /* Exception Interrupt Port/Queue Cause register
@@ -1022,20 +1023,30 @@ static void mvneta_defaults_set(struct mvneta_port *pp)
 	/* Enable MBUS Retry bit16 */
 	mvreg_write(pp, MVNETA_MBUS_RETRY, 0x20);
 
-	/* Set CPU queue access map. CPUs are assigned to the RX
-	 * queues modulo their number and all the TX queues are
-	 * assigned to the CPU associated to the default RX queue.
+	/* Set CPU queue access map. CPUs are assigned to the RX and
+	 * TX queues modulo their number. If there is only one TX
+	 * queue then it is assigned to the CPU associated to the
+	 * default RX queue.
 	 */
 	for_each_present_cpu(cpu) {
 		int rxq_map = 0, txq_map = 0;
-		int rxq;
+		int rxq, txq;
 
 		for (rxq = 0; rxq < rxq_number; rxq++)
 			if ((rxq % max_cpu) == cpu)
 				rxq_map |= MVNETA_CPU_RXQ_ACCESS(rxq);
 
-		if (cpu == pp->rxq_def)
-			txq_map = MVNETA_CPU_TXQ_ACCESS_ALL_MASK;
+		for (txq = 0; txq < txq_number; txq++)
+			if ((txq % max_cpu) == cpu)
+				txq_map |= MVNETA_CPU_TXQ_ACCESS(txq);
+
+		/* With only one TX queue we configure a special case
+		 * which will allow to get all the irq on a single
+		 * CPU
+		 */
+		if (txq_number == 1)
+			txq_map = (cpu == pp->rxq_def) ?
+				MVNETA_CPU_TXQ_ACCESS(1) : 0;
 
 		mvreg_write(pp, MVNETA_CPU_MAP(cpu), rxq_map | txq_map);
 	}
@@ -1824,13 +1835,16 @@ error:
 static int mvneta_tx(struct sk_buff *skb, struct net_device *dev)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
-	u16 txq_id = skb_get_queue_mapping(skb);
+	u16 txq_id = smp_processor_id() % txq_number;
 	struct mvneta_tx_queue *txq = &pp->txqs[txq_id];
 	struct mvneta_tx_desc *tx_desc;
 	int len = skb->len;
 	int frags = 0;
 	u32 tx_cmd;
 
+	/* Use the tx queue bound to this CPU */
+	skb_set_queue_mapping(skb, txq_id);
+
 	if (!netif_running(dev))
 		goto out;
 
@@ -2811,13 +2825,23 @@ static void mvneta_percpu_elect(struct mvneta_port *pp)
 			if ((rxq % max_cpu) == cpu)
 				rxq_map |= MVNETA_CPU_RXQ_ACCESS(rxq);
 
-		if (i == online_cpu_idx) {
-			/* Map the default receive queue and transmit
-			 * queue to the elected CPU
+		if (i == online_cpu_idx)
+			/* Map the default receive queue queue to the
+			 * elected CPU
 			 */
 			rxq_map |= MVNETA_CPU_RXQ_ACCESS(pp->rxq_def);
-			txq_map = MVNETA_CPU_TXQ_ACCESS_ALL_MASK;
-		}
+
+		/* We update the TX queue map only if we have one
+		 * queue. In this case we associate the TX queue to
+		 * the CPU bound to the default RX queue
+		 */
+		if (txq_number == 1)
+			txq_map = (i == online_cpu_idx) ?
+				MVNETA_CPU_TXQ_ACCESS(1) : 0;
+		else
+			txq_map = mvreg_read(pp, MVNETA_CPU_MAP(cpu)) &
+				MVNETA_CPU_TXQ_ACCESS_ALL_MASK;
+
 		mvreg_write(pp, MVNETA_CPU_MAP(cpu), rxq_map | txq_map);
 
 		/* Update the interrupt mask on each CPU according the
-- 
2.5.0